Predictive Recommendations for Diabetes using Ensemble Techniques with Model Explanations
Keywords:
Machine Learning, Predictive recommendations, Ensemble, SHAP, Diabetes mellitusAbstract
The modern life-style and post corona impressions have impacted the public health with unending medical issues. The facts-figures of International Diabetes Federation (IDF) Atlas depicted that approximately 11% of the adults along with the teenagers are having one of the major non-communicable diseases called diabetes while few of them are still ignorant about the health disorders. The precautionary measures must be taken to minimize the effect of diabetes by furnishing premature diagnosis and thus assist the people to evade the medical complications. The proposed study delves into the medical data with electronic health records and various learning models with advanced algorithmic techniques. The research outcome based on predictive recommendations helps to portray the safety measures to avoid health hazards. The proposed algorithm with ensemble approach that aims to combine different algorithmic techniques and weighted probability for the heterogeneous data performs better with optimized estimates and model explanations using SHAP. The state-of-art-study depicts that a good sense of disease understanding can help to improve almost every facet of health sustainability and motivate the society to know the at-risk health alerts in advance. The study focuses on ensemble model with gradient boost, random forest, extreme gradient boosting, etc. to depict the reliability of proposed technique and demonstrate the comparative analysis with various benchmark datasets.
Downloads
References
Luis Fregoso‑Aparicio, Julieta Noguez, Luis Montesinos and José A. García‑García, “Machine learning and deep learning predictive models for type 2 diabetes: a systematic review,” Diabetology & Metabolic Syndrome, 2021, Vol.13. Isuue.148, pp.1-22, doi.org/10.1186/s13098-021-00767-9
P. Colmegna et al., "Evaluation of a Web-Based Simulation Tool for Self-Management Support in Type 1 Diabetes: A Pilot Study," in IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 1, pp. 515-525, Jan. 2023, doi: 10.1109/JBHI.2022.3209090.
Uzma Ghulam Mohammad,Salma Imtiaz, Manoj Shakya, Ahmad Almadhor and Fareeha Anwar, “An Optimized Feature Selection Method Using Ensemble Classifiers in Software Defect Prediction for Healthcare Systems,” Vol.22, Article ID 1028175 , pp.1-14, Jun’2022.
Ghorpade, J., & Sonkamble, B., “Data-driven based Optimal Feature Selection Algorithm using Ensemble Techniques for Classification,” International Journal on Recent and Innovation Trends in Computing and Communication, Vol.11, Issue.4, pp.33–41.
Agliata A, Giordano D, Bardozzo F, Bottiglieri S, Facchiano A, Tagliaferri R., “Machine Learning as a Support for the Diagnosis of Type 2 Diabetes”, International Journal of Molecular Sciences. 2023; 24(7):6775.
I. D. Mienye and Y. Sun, "A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects," in IEEE Access, vol. 10, pp. 99129-99149, 2022, doi: 10.1109/ACCESS.2022.3207287.
Webb, G. I., & Zheng, Z., “Multistrategy Ensemble Learning: Reducing Error by Combining Ensemble Learning Techniques,” IEEE Transactions on Knowledge and Data Engineering, 16(8), 980-991, 2004.
Dutta, A.; Hasan, M.K.; Ahmad, M.; Awal, M.A.; Islam, M.A.; Masud, M.; Meshref, H. Early, ‘Prediction of Diabetes Using an Ensemble of Machine Learning Models. Int. J. Environ. Res. Public Health 2022, 19, 12378.
E. D. Spyrou and V. Kappatos, "XAI using SHAP for Outdoor-to-Indoor 5G Mid-Band Network," 2023 IEEE 12th International Conference on Communication Systems and Network Technologies (CSNT), Bhopal, India, 2023, pp. 862-866, doi: 10.1109/CSNT57126.2023.10134625.
D. Fryer, I. Strümke and H. Nguyen, "Shapley Values for Feature Selection: The Good, the Bad, and the Axioms," in IEEE Access, vol. 9, pp. 144352-144360, 2021, doi: 10.1109/ACCESS.2021.3119110.
B. Shamreen Ahamed, Meenakshi Arya, Auxilia Osvin Nancy, “Prediction of Type-2 Diabetes Mellitus Disease Using Machine Learning Classifiers and Techniques”, Front. Comput. Sci., 10 May 2022.
F. Sambo et al., "A Bayesian Network analysis of the probabilistic relations between risk factors in the predisposition to type 2 diabetes," 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy, 2015, pp. 2119-2122.
Diabetes, 5April’2023, World Health Organization Newsroom, https://www.who.int/news-/ news-room/fact-sheets/detail/diabetes
Karina W. Davidson, PhD, MASc, “Screening for Prediabetes and Type 2 Diabetes US Preventive Services Task Force Recommendation Statement”, JAMA. Aug’2021, Vol.326, Issue.8, pp.736-743. doi:10.1001/jama.2021.12531
Narges Razavian, Saul Blecker, Ann Marie Schmidt, Aaron Smith-McLallen, Somesh Nigam, and David Sontag, "Population-Level Prediction of Type 2 Diabetes from Claims Data and Analysis of Risk Factors", Big Data 2015, Vol3(4), pp.277-287.
N. S. Choudary, V. B. Bommineni, G. Tarun, G. P. Reddy and G. Gopakumar, "Predicting Covid-19 Positive Cases and Analysis on the Relevance of Features using SHAP (SHapley Additive exPlanation)," 2021 Second International Conference on Electronics and Sustainable Communication Systems (ICESC), India, 2021, pp. 1892-1896.
Martin Jullum, Annabelle Redelmeier and Kjersti Aas, “Efficient and simple prediction explanations with groupShapley: A practical perspective,” XAI.it 21 - Italian Workshop on Explainable Artificial Intelligence, 2021, pp.1-15
Bloch, L., Friedrich, C.M. & for the Alzheimer’s Disease Neuroimaging Initiative, ‘Data analysis with Shapley values for automatic subject selection in Alzheimer’s disease data sets using interpretable machine learning,’ Alz Res Therapy 13, 155 (2021).
Ruchika Malhotra, Anjali Sharma, “Threshold benchmarking for feature ranking techniques”, Bulletin of Electrical Engineering and Informatics, Vol. 10, No. 2, April 2021, ISSN: 2302-9285, pp. 1063-1070.
Lv, Fan & Gao, Xu & Huang, Amy & Zu, Jian & He, Xinyuan & Sun, et. al.,“Excess diabetes mellitus-related deaths during the COVID-19 pandemic in the United States,” eClinical Medicine, Vol.54. 2022.
Nowakowska, M., Zghebi, S.S., Ashcroft, D.M. et al. The comorbidity burden of type 2 diabetes mellitus: patterns, clusters and predictions from a large English primary care cohort. BMC Med 17, 145 (2019).
Saarela, M., Jauhiainen, S., “Comparison of feature importance measures as explanations for classification models,” SN Appl. Sci. Vol.3, Issue.272, 2021, doi.org/10.1007/s42452-021-04148-9)
Kuhn HW, Tucker AW, ‘Shapley LS. A value for n-person games’, Contributions to the Theory of Games. vol. 2. Princeton, US: Princeton University Press; 1953. p. 307{318.doi:10.1515/9781400881970-018.
24. Diabetes and Asian Americans. Centers for Disease Control and Prevention. https://www.cdc.gov/diabetes/library/spotlights/diabetes-asian-americans.html
Wu, C., Wu, J., Luo, C. et al., “Recommendation algorithm based on user score probability and project type,” J Wireless Com Network, 2019, 80.
Glauber H, Vollmer WM, Nichols GA, “A Simple Model for Predicting Two-Year Risk of Diabetes Development in Individuals with Prediabetes”, Perm J. 2018; 22:17-050.
Chukwuebuka Ejiyi, Zhen Qin, Joan Amos, Makuachukwu Ejiyi, Ann Nnani, Thomas Ugochukwu, Victor Kwaku Agbesi, Chidimma D., Chidinma O., "A robust predictive diagnosis model for diabetes mellitus using Shapley-incorporated machine learning algorithms," Healthcare Analytics, Vol.3, 2023, 100166, ISSN 2772-4425.
V. Jackins, S. Vimal, M. Kaliappan, M. Y. Lee, “AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes,” Fe Journal of Supercomputing, vol. 77, no. 5, pp. 5198–5219, 2021.
Mohapatra, S.K., Swain, J.K., Mohanty, M.N. (2019). “Detection of Diabetes Using Multilayer Perceptron,” In: Bhaskar, M., Dash, S., Das, S., Panigrahi, B. (eds) International Conference on Intelligent Computing and Applications. Advances in Intelligent Systems and Computing, vol 846. Springer, Singapore. https://doi.org/10.1007/978-981-13-2182-5_11.
Sisodia, D., & Sisodia, D.S., ‘Prediction of Diabetes using Classification Algorithms’. Procedia Computer Science, Vol.132, 2018, pp.1578-1585.
Tasin, I., Nabil, T.U., Islam, S., Khan, R.,”Diabetes prediction using machine learning and explainable AI techniques,” Healthc. Technol. Lett. 10, 1–10 (2023). https://doi.org/10.1049/htl2.12039.
Saloni Kumari, Deepika Kumar, Mamta Mittal, “An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier,” 'International Journal of Cognitive Computing in Engineering,' Volume 2, 2021, Pages 40-46, ISSN 2666-3074.
Saiteja C., Gahangir H., Ayush Goyal, Anupama B., Sayantan B., Devottam Gaurav, Sanju Mishra, “Smart home health monitoring system for predicting type 2 diabetes and hypertension,” Journal of King Saud University - Computer and Information Sciences, Vol.34(3), 2022, pp.862-870, ISSN 1319-1578.
Joshi RD, Dhakal CK., “Predicting Type 2 Diabetes Using Logistic Regression and Machine Learning Approaches,” International Journal of Environmental Research and Public Health. 2021; 18(14):7346.
Ramasamy, J. ., Doshi, R. ., & Hiran, K. K. . (2023). Three Step Authentication of Brain Tumour Segmentation Using Hybrid Active Contour Model and Discrete Wavelet Transform. International Journal on Recent and Innovation Trends in Computing and Communication, 11(3s), 56–64. https://doi.org/10.17762/ijritcc.v11i3s.6155
Robert Roberts, Daniel Taylor, Juan Herrera, Juan Castro, Mette Christensen. Enhancing Collaborative Learning through Machine Learning-based Tools. Kuwait Journal of Machine Learning, 2(1). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/view/177
Agrawal, S.A., Umbarkar, A.M., Sherie, N.P., Dharme, A.M., Dhabliya, D. Statistical study of mechanical properties for corn fiber with reinforced of polypropylene fiber matrix composite (2021) Materials Today: Proceedings, .
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
